Project Associate

Job Description

Job Description: We are looking for a passionate and talented Machine Learning Engineer with expertise in Speech Processing to join our team. This role offers the opportunity to work on cutting-edge technologies, develop state-of-the-art solutions, and make a real impact in the field of audio and speech applications. Educational Qualifications: Master’s or PhD in Electrical Engineering, Computer Science, Artificial Intelligence, Machine Learning, or a related field with a specialization in Speech Processing. Key Responsibilities: Design and develop advanced machine learning algorithms and pipelines for audio and speech generative models, aiming to achieve state-of-the-art (SOTA) performance. Work hands-on with frameworks for Speaker Diarization , Source Separation , Noise Cancellation , Speaker Recognition , and Automatic Speech Recognition (ASR) . Should be able to build text-to-speech (TTS) synthesizers along with integrated features like voice cloning Emotion Control, Accent Flexibility, Pitch variation, and Expressivity. Research and implement speech-to-speech translation (S2ST) systems with a focus on improving accuracy and efficiency. Conduct experiments on large-scale datasets and address challenges related to domain-shifted conditions. Collaborate with cross-functional teams to integrate speech models into real-world applications. Stay up-to-date with the latest advancements in speech processing and explore ways to apply them effectively. Requirements: Proven experience in implementing and optimizing SOTA frameworks for Speaker Diarization , Source Separation , Noise Cancellation , Speaker Recognition , and ASR . Must have experience working with SOTA TTS frameworks or models, along with a solid understanding of integrating advanced features such as Voice Cloning (including zero-shot, cross-lingual, and code-switched speech generation), Emotion Control, Accent Flexibility, Pitch Variation, and Expressivity. Practical knowledge of handling large-scale datasets and managing experiments under domain shifted conditions. Expertise in S2ST systems and their end-to-end development. Strong programming skills in Python and experience with frameworks such as TensorFlow or PyTorch.